通过学习笔画间偏移属性，实现更自然的草图笔画级编辑。
Refining Strokes by Learning Offset Attributes between Strokes for Flexible Sketch Edit at Stroke-Level
- 学习缩放、方向和位置三类偏移属性，精准调整源笔画。
- 在多个数据集上实现高精度笔画级编辑，视觉一致性显著提升。
- 适合需要精细控制草图编辑的设计师或研究者使用。
笔画级草图编辑旨在通过笔画扩展或替换，将源笔画移植到目标草图上，同时保持语义一致性和视觉保真度。现有方法仅通过重新定位源笔画来实现，但因源笔画在尺寸和方向上存在显著差异，单纯重定位难以生成合理结果。例如，若未按比例缩放就直接锚定过大的源笔画，会导致语义不连贯。为此，本文提出 SketchMod，通过变换源笔画以匹配目标草图的模式，实现灵活的笔画级编辑。由于源笔画的优化依赖于目标草图的模式，我们从源笔画中学习三个关键偏移属性（缩放、方向、位置），并通过：1）按比例缩放以匹配空间比例；2）旋转对齐局部几何；3）平移以契合语义布局，实现对齐。此外，编辑过程中可精确控制笔画特征。实验表明，SketchMod 在笔画级草图编辑上表现出高精度与灵活性。
原文摘要 · Abstract (English)
Sketch edit at stroke-level aims to transplant source strokes onto a target sketch via stroke expansion or replacement, while preserving semantic consistency and visual fidelity with the target sketch. Recent studies addressed it by relocating source strokes at appropriate canvas positions. However, as source strokes could exhibit significant variations in both size and orientation, we may fail to produce plausible sketch editing results by merely repositioning them without further adjustments. For example, anchoring an oversized source stroke onto the target without proper scaling would fail to produce a semantically coherent outcome. In this paper, we propose SketchMod to refine the source stroke through transformation so as to align it with the target sketch's patterns, further realize flexible sketch edit at stroke-level. As the source stroke refinement is governed by the patterns of the target sketch, we learn three key offset attributes (scale, orientation and position) from the source stroke to another, and align it with the target by: 1) resizing to match spatial proportions by scale, 2) rotating to align with local geometry by orientation, and 3) displacing to meet with semantic layout by position. Besides, a stroke's profiles can be precisely controlled during sketch edit via the exposed captured stroke attributes. Experimental results indicate that SketchMod achieves precise and flexible performances on stroke-level sketch edit.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。